INDEX

Explanations

words related to revising, amending, and updating laws or regulations

oai_token-act-pair · gpt-3.5-turbo

words related to changes or modifications in laws or regulations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agos

-0.74

ngth

-0.72

cium

-0.67

ffield

-0.67

ulhu

-0.66

 istg

-0.65

zin

-0.65

âĹ¼

-0.64

eous

-0.64

emies

-0.64

POSITIVE LOGITS

 outdated

1.05

 existing

1.03

how

0.96

 regulations

0.95

 wording

0.93

 terminology

0.91

 rules

0.91

 procedures

0.88

 Regulations

0.85

 guidelines

0.81

Activations Density 0.194%

words related to revising, amending, and updating laws or regulations

words related to changes or modifications in laws or regulations

No Comments

No Known Activations